Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring

TL;DR

This paper presents a multi-agent framework called the Advisory Governance Layer (AGL) that enables multi-stakeholder participation and governance in LLM-powered Intelligent Tutoring Systems, addressing conflicts and ensuring accountability.

Contribution

It introduces a novel multi-agent architecture with conflict-resolution protocols for aligning AI systems with diverse stakeholder values in education.

Findings

Designed a privacy-preserving stakeholder evaluation mechanism

Developed a structured policy taxonomy for conflict resolution

Provided technical specifications for multi-stakeholder AI governance

Abstract

The integration of Large Language Models into Intelligent Tutoring Systems pre-sents significant challenges in aligning with diverse and often conflicting values from students, parents, teachers, and institutions. Existing architectures lack for-mal mechanisms for negotiating these multi-stakeholder tensions, creating risks in accountability and bias. This paper introduces the Advisory Governance Layer (AGL), a non-intrusive, multi-agent framework designed to enable distributed stakeholder participation in AI governance. The AGL employs specialized agents representing stakeholder groups to evaluate pedagogical actions against their spe-cific policies in a privacy-preserving manner, anticipating future advances in per-sonal assistant technology that will enhance stakeholder value expression. Through a novel policy taxonomy and conflict-resolution protocols, the frame-work provides structured, auditable governance advice to the ITS without altering its core pedagogical decision-making. This work contributes a reference architec-ture and technical specifications for aligning educational AI with multi-stakeholder values, bridging the gap between high-level ethical principles and practical implementation.